sexual situations

physical violence

disturbing

male nudity

extremist

hanging

hate symbols

nazi party

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

self injury

graphic violence or gore

graphic female nudity

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

suggestive

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

sexy

nsfw

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

TRPCError

<a target="_blank" rel="ugc" href="https://www.instagram.com/priricart/?hl=en">Priscilla Ricart </a>is a Brazilian model and social media star based in Miami. For her TI, I used 25 images taken from her Insta account. <s>After a failed try (using the same parameters as in Maria Guardiola's TI), I changed to a fixed learning rate (of about 0.003) and interrupted the process at only 1615 steps. </s>This TI has been updated. Please check the "About this version" section!

Actually, I've been testing the 1500-step version and it seems much improved, so I'm uploading this one too. While testing, I've sometimes found results that make me think the TI's on the verge of being overtrained, so I will stop training this model here.

v2.1

I'm uploading an alternate model that feels more accurate, in my opinion. I've altered my working process a little bit in the last few days. First of all, I don't use the "Use PNG alpha channel as loss weight" anymore, as I felt my embeddings were getting overtrained almost from the start. I have a more active approach now too: I begin with a flat learning rate of around 0.004 and patiently wait until I get some decent pic resembling the subject, which usually doesn't take more than 400 steps anyway. Then I interrupt the process, test the result and reduce the learning rate to maybe 0.001. Run the process for a few more hundred steps and usually I already get a decent TI at least. I guess I'll keep improving the process as I run more tests, but for the time being I'm happy with these results. Hope you like it!

v2.0

v1.0

Priscilla Ricart

avatar01.jpg

Type	Embedding
Stats	1,434
Reviews	Very Positive (130)
Published	Jun 23, 2023
Base Model	SD 1.5
Training	Steps: 1,500
Trigger Words	priricart
Hash	AutoV2 D549581CA9